Fast and Accurate Error Simulation for CNNs against Soft Errors
The great quest for adopting AI-based computation for safety-/mission-critical applications motivates the interest towards methods for assessing the robustness of the application w.r.t. not only its training/tuning but also errors due to faults, in particular soft errors, affecting the underlying hardware. Two strategies exist: architecture-level fault injection and application-level functional error simulation. We present a framework for the reliability analysis of Convolutional Neural Networks (CNNs) via an error simulation engine that exploits a set of validated error models extracted from a detailed fault injection campaign. These error models are defined based on the corruption patterns of the output of the CNN operators induced by faults and bridge the gap between fault injection and error simulation, exploiting the advantages of both approaches. We compared our methodology against SASSIFI for the accuracy of functional error simulation w.r.t. fault injection, and against TensorFI in terms of speedup for the error simulation strategy. Experimental results show that our methodology achieves about 99\% accuracy of the fault effects w.r.t. SASSIFI, and a speedup ranging from 44x up to 63x w.r.t. TensorFI, that only implements a limited set of error models.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Fast and accurate learned multiresolution dynamical downscaling for precipitation
This study develops a neural network-based approach for emulating high-resolution modeled precipitation data with comparable statistical properties but at greatly reduced computational cost. The key idea is to use combin…
CPUGenerative Adversarial NetworkGPUSuper-ResolutionCNNSAT: Fast, Accurate Boolean Satisfiability using Convolutional Neural Networks
Boolean satisfiability (SAT) is one of the most well-known NP-complete problems and has been extensively studied. State-of-the-art solvers exist and have found a wide range of applications. However, they still do not sc…
A Study of All-Convolutional Encoders for Connectionist Temporal Classification
Connectionist temporal classification (CTC) is a popular sequence prediction approach for automatic speech recognition that is typically used with models based on recurrent neural networks (RNNs). We explore whether deep…
AllAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Classification+3HarDNN: Feature Map Vulnerability Evaluation in CNNs
As Convolutional Neural Networks (CNNs) are increasingly being employed in safety-critical applications, it is important that they behave reliably in the face of hardware errors. Transient hardware errors may percolate u…
Decision MakingFast and Accurate Reduced-Order Modeling of a MOOSE-based Additive Manufacturing Model with Operator Learning
One predominant challenge in additive manufacturing (AM) is to achieve specific material properties by manipulating manufacturing process parameters during the runtime. Such manipulation tends to increase the computation…
Dimensionality ReductionOperator learning